检索结果-内蒙古大学图书馆

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

学校读者我要写书评

暂无评论

Detecting Backdoors During the Inference Stage Based on Corr...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Xiaogeng Liu Minghui Li Haoyu Wang Shengshan Hu Dengpan Ye Hai Jin Libing Wu Chaowei Xiao School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Software Engineering Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan University School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab Arizona State University

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo) 1 1 https://***/CGCL-codes/TeCo, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability.

关键词：

Moto: Enhancing Embedding with Multiple Joint Factors for Chinese Text Classification

学校读者我要写书评

暂无评论

Moto: Enhancing Embedding with Multiple Joint Factors for Ch...

International Conference on Pattern Recognition

作者： Xunzhu Tang Rujie Zhu Tiezhu Sun Shi Wang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China University of Central Florida Orlando FL USA Momenta Suzhou China Institute of Computing Technology Chinese Academy beijing China

Recently, language representation techniques have achieved great performances in text classification. However, most existing representation models are specifically designed for English materials, which may fail in Chinese because of the huge difference between these two languages. Actually, few existing methods for Chinese text classification process texts at a single level. However, as a special kind of hieroglyphics, radicals of Chinese characters are good semantic carriers. In addition, Pinyin codes carry the semantic of tones, and Wubi reflects the stroke structure information, etc. Unfortunately, previous researches neglected to find an effective way to distill the useful parts of these four factors and to fuse them. In our works, we propose a novel model called Moto: Enhancing Embedding with Multiple Joint Factors. Specifically, we design an attention mechanism to distill the useful parts by fusing the four-level information above more effectively. We conduct extensive experiments on four popular tasks. The empirical results show that our Moto achieves SOTA 0.8316 (F₁-score, 2.11% improvement) on Chinese news titles, 96.38 (1.24% improvement) on Fudan Corpus and 0.9633 (3.26% improvement) on THUCNews.

关键词： Fuses Text categorization Semantics Pattern recognition Task analysis

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensional Input Spaces

学校读者我要写书评

暂无评论

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensiona...

International Conference on Software Engineering (ICSE)

作者： Haoxiang Jia Ming Wen Zifan Xie Xiaochen Guo Rongxin Wu Maolin Sun Kang Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology China Hubei Key Laboratory of Distributed System Security Services Computing Technology and System Lab Cluster and Grid Computing Lab. Hubei Engineering Research Center on Big Data Security National Engineering Research Center for Big Data Technology and System School of Informatics Xiamen University China School of Computer Science and Technology Huazhong University of Science and Technology China

Java Virtual Machine (JVM) is the fundamental software system that supports the interpretation and execution of Java bytecode. To support the surging performance demands for the increasingly complex and large-scale Java programs, Just-In-Time (JIT) compiler was proposed to perform sophisticated runtime optimization. However, this inevitably induces various bugs, which are becoming more pervasive over the decades and can often cause significant consequences. To facilitate the design of effective and efficient testing techniques to detect JIT compiler bugs. This study first performs a preliminary study aiming to understand the characteristics of JIT compiler bugs and the corresponding triggering test cases. Inspired by the empirical findings, we propose JOpFuzzer, a new JVM testing approach with a specific focus on JIT compiler bugs. The main novelty of JOpFuzzer is embodied in three aspects. First, besides generating new seeds, JOpFuzzer also searches for diverse configurations along the new dimension of optimization options. Second, JOpFuzzer learns the correlations between various code features and different optimization options to guide the process of seed mutation and option exploration. Third, it leverages the profile data, which can reveal the program execution information, to guide the fuzzing process. Such nov-elties enable JOpFuzzer to effectively and efficiently explore the two-dimensional input spaces. Extensive evaluation shows that JOpFuzzer outperforms the state-of-the-art approaches in terms of the achieved code coverages. More importantly, it has detected 41 bugs in OpenJDK, and 25 of them have already been confirmed or fixed by the corresponding developers.

关键词：

Efficient dynamic evolution of service composition

学校读者我要写书评

暂无评论

Efficient dynamic evolution of service composition

作者： Lv, Chen Jiang, Wei Hu, Songlin Wang, Jiye Lu, Guoliang Liu, Zhiyong School of Information Science and Engineering Shandong Normal University China Greatwall Drilling Company R&D Academy of Well Logging CNPC Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China Department of Information Technology State Grid Corporation of China Beijing China School of Mechanical Engineering Shandong University China Institute of Computing Technology Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China

Current QoS-aware automatic service composition queries over a network of web services are often one-time in nature. After a network of web services is built, such queries are issued once, and answers are found from the scratch. The underlying assumption is that the participating web services are rather static, which means that their functional and non-functional parameters seldom change. However, such an assumption is often baseless. New services come and go, service APIs change gradually, and QoS values fluctuate in practice. Therefore, a support for efficiently adapting service composition is desired. In this paper, we propose an event driven continuous query algorithm to intelligently cope with different types of dynamic services, and thus enable evolution of service composition. Evaluation using both real QoS data and synthetic web service data shows its superior performance, compared with the state-of-the-art solution which won the performance championship of Web Service Challenge in 2009 and 2010. Moreover, we generalize a new graph problem: dynamic single-source optimal-Directed Acyclic Graphs (DAG) problem based on the above work. It is argued that API recommendation for framework evolution, as another typical application, could also be modeled and addressed efficiently using the proposed new graph approach. © 2017 IEEE.

关键词： Web services

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Jialuo Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Our code is available at https://***/Gp1g/FedAA. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Ziqi Li, Bowen Song, Yufei Yu, Zhifei Hu, Shengshan Wan, Wei Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the advancement of deep learning, object detectors (ODs) with various architectures have achieved significant success in complex scenarios like autonomous driving. Previous adversarial attacks against ODs have been focused on designing customized attacks targeting their specific structures (e.g., NMS and RPN), yielding some results but simultaneously constraining their scalability. Moreover, most efforts against ODs stem from image-level attacks originally designed for classification tasks, resulting in redundant computations and disturbances in object-irrelevant areas (e.g., background). Consequently, how to design a model-agnostic efficient attack to comprehensively evaluate the vulnerabilities of ODs remains challenging and unresolved. In this paper, we propose NumbOD, a brand-new spatial-frequency fusion attack against various ODs, aimed at disrupting object detection within images. We directly leverage the features output by the OD without relying on its internal structures to craft adversarial examples. Specifically, we first design a dual-track attack target selection strategy to select high-quality bounding boxes from OD outputs for targeting. Subsequently, we employ directional perturbations to shift and compress predicted boxes and change classification results to deceive ODs. Additionally, we focus on manipulating the high-frequency components of images to confuse ODs' attention on critical objects, thereby enhancing the attack efficiency. Our extensive experiments on nine ODs and two datasets show that NumbOD achieves powerful attack performance and high stealthiness. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

Vflh: A Following-the-Leader-History Based Algorithm for Adaptive Online Convex Optimization with Stochastic Constraints

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Yang, Yifan Chen, Lin Zhou, Pan Ding, Xiaofeng Department of Computer Science University of California Santa BarbaraCA93106 United States National Engineering Research Center for Big Data Technology and System Lab Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan430072 China

This paper considers online convex optimization (OCO) with generated i.i.d. stochastic constraints, where the distribution of environment is changing and the performance is measured by \textit{adaptive regret}. The stochastic constraints are disclosed at each round to the learner after the decision is made. Different from the previous non-adaptive constrained OCO algorithm which is generalized based on the traditional online gradient descent algorithm, we propose a novel \textit{Virtual queue based Following-the-Leader-History} (VFLH) strategy to make the constrained OCO algorithm adaptive and design the VFLH algorithm. In this setting, the algorithm firstly generalizes all the experts in the specified time interval, then decides the optimal decision with each expert and gives out the final choice by combining the predictions of active experts. In terms of the algorithm performance, there are two performance metrics to be evaluated, i.e., the bounds of constraint violation and regret. For the constraint violation, we bring in the multi-objective drift analysis approach to deal with the constraints via a virtual queue which provides a new method to bound the constraints violations. For the regret, we give out its upper bound and then achieve a corresponding lower bound that proves the upper bound is sufficiently tight. Finally, we provide some numerical experiments to validate the feasibility of our algorithm. © 2022, The Authors. All rights reserved.

关键词： Stochastic systems

Clairvoyance: Intelligent route planning for electric buses based on urban big data

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lu, Xiangyong Ota, Kaoru Dong, Mianxiong Yu, Chen Jin, Hai Graduate School of Information Sciences Tohoku University Sendai Japan Serviecs Computing Technology and System Lab Big Data Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Information and Electronic Engineering Muroran Institute of Technology Hokkaido Muroran Japan

Nowadays many cities around the world have introduced electric buses to optimize urban traffic and reduce the local carbon emissions. In order to cut the carbon emissions and maximize the utility of electric buses, it is important to choose suitable routes for them. Traditionally, route selection is on the basis of dedicated surveys, which are costly in time and labor. In this paper, we mainly focus attention on planning electric bus routes intelligently, depending on the unique needs of each region throughout the city. We propose Clairvoyance, a route planning system that leverages a deep neural network and a multilayer perceptron to predict the future people’s trips and the future transportation carbon emission in the whole city, respectively. Given the future information of people’s trips and transportation carbon emission, we utilize a greedy mechanism to recommend bus routes for electric buses that will depart in an ideal state. Furthermore, representative features of the two neural networks are extracted from the heterogeneous urban datasets. We evaluate our approach through extensive experiments on the real-world data sources in Zhuhai, China. The results show that our designed neural network-based algorithms are consistently superior to the typical baselines. Additionally, the recommended routes for electric buses are helpful in reducing the peak value of carbon emissions and making full use of electric buses in the city. Copyright © 2021, The Authors. All rights reserved.

关键词： Multilayer neural networks

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of School of Software Engineering Huazhong University of Science and Technology China

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model’s incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method’s superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method’s effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks